Portable Inference

Friday 4 Dec 2020, 09:30 → 13:00 America/Chicago

Virtual (Zoom)

Mark Neubauer (Univ. Illinois at Urbana Champaign (US)), Javier Mauricio Duarte (Univ. of California San Diego (US)), Allison Mccarn Deiana (Southern Methodist University (US)), Philip Coleman Harris (Massachusetts Inst. of Technology (US)), Shih-Chieh Hsu (University of Washington Seattle (US)), Maurizio Pierini (CERN)

We are pleased a mini-workshop (1/2 day) event “Portable Inference”, which will be held virtually on December 4, 2020. This virtual workshop is a satellite meeting co-"located" with the Fast Machine Learning Workshop a Blueprint meeting of the Institute for Research and Innovation for Software in High-Energy Physics (IRIS-HEP). 

The goal of this workshop is to bring together experts to share their experiences, on-going work and plans in area of portable inference. The workshop is meant to be an informal technical interchange between experiments and split 50/50 between short presentations and discussions. During the discussion block, we would like to develop a short document which identifies common challenges around portable inference for co-processing applications (e.g. High-level Trigger, analysis) and points of future collaboration. 

All participants in this workshop must abide to the IRIS-HEP Code-of-Conduct found at https://iris-hep.org/about/code-of-conduct

ZOOM link: https://illinois.zoom.us/j/87610344289?pwd=NnpZU0tWOU9vNmRPR3gyNXI3aGRPUT09

Live Notes

09:30 → 09:40 Workshop Overview and Goals (10')

Speaker: Mark Neubauer (Univ. Illinois at Urbana Champaign (US))

Blueprint_Intro_Portable_Inference.pdf

Blueprint_Intro_Portable_Inference.pptx

09:40 → 09:50 Highlights and Takeaways from the FastML Workshop (10')

Speaker: Nhan Viet Tran (Fermi National Accelerator Lab. (US))

slides

09:50 → 10:00 Co-Processor Activities within FastML (10')

Speakers: Miaoyuan Liu (Purdue University (US)), Markus Julian Atkinson (Univ. Illinois at Urbana Champaign (US))

fastml-coprocessor-group.pdf

10:00 → 10:15 Fast ML Inference as a service (10' + 5')

Speaker: Dylan Sheldon Rankin (Massachusetts Inst. of Technology (US))

fastml_aas_04dec20.pdf

10:15 → 10:30 ML Frameworks in CMSSW (10' + 5')

Speaker: Kevin Pedro (Fermi National Accelerator Lab. (US))

cmssw ml dec 4 2020.pdf

10:30 → 10:45 ML frameworks in Athena (10' + 5')

Speaker: Mr Debottam Bakshi Gupta (University of Texas at Arlington (US))

FastML_2020.pdf

10:45 → 11:00 ML Frameworks in DUNE (10' + 5')

Speakers: Leigh Howard Whitehead (University of Cambridge (GB)), Leigh Whitehead (University of Warwick)

lhw_DUNE_DL_Workshop_041220.pdf

11:00 → 11:10 Fitting & Statistical Inference as a Service (8' + 2')

Speaker: Matthew Feickert (Univ. Illinois at Urbana Champaign (US))

Feickert_2020-12-04.pdf

11:10 → 11:30 Break

11:30 → 13:00 Discussion, Writing & Next Steps